Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    fellow members, citizens, enthusiasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     A
    0.89
    c
    0.85
    ع
    0.84
     I
    0.79
     Alek
    0.76
    t
    0.76
    h
    0.75
    墘
    0.75
    ע
    0.72
     on
    0.72
    POSITIVE LOGITS
    ARE
    0.79
    는
    0.77
    ों
    0.75
    みの
    0.66
     disparities
    0.65
    osta
    0.63
     membro
    0.63
    oms
    0.62
     distortions
    0.62
    ও
    0.61
    Act Density 0.009%

    No Known Activations